Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1178. Min Act: -0.0001

Data Index: 429134 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0001

Data Index: 54699 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1077. Min Act: -0.0001

Data Index: 103938 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1102157 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1158616 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1287903 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1096. Min Act: -0.0001

Data Index: 7232 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1055. Min Act: -0.0001

Data Index: 932134 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1092. Min Act: -0.0001

Data Index: 419084 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1111063 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1033201 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1093. Min Act: -0.0001

Data Index: 665487 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1063. Min Act: -0.0001

Data Index: 197356 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1084. Min Act: -0.0001

Data Index: 698106 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1173748 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1056. Min Act: -0.0001

Data Index: 622599 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1031. Min Act: -0.0001

Data Index: 955234 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0906. Min Act: -0.0001

Data Index: 920032 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0928. Min Act: -0.0001

Data Index: 359635 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1302948 (C4 (Web Text))

Max Activating Token Index: 793